docs: delete the "why not stack every plugin" section

The section only made sense when this package was framed as a merge of many
upstream packages. Now that the five layers are described as this project's
own design, the whole chapter is noise - and its title alone suggests stacking
plugins, which is the opposite of the point.

- README.md: 8639 -> 7940 chars
- README.en.md: 9336 -> 7798 chars
- remaining sections: intro / architecture / five layers / install / verify /
  config / relationship / uninstall / FAQ / tree / license / screenshots
This commit is contained in:
moyun-ultimate 2026-11-16 14:19:45 +08:00
parent 033c3d158f
commit afd3d62986
2 changed files with 0 additions and 52 deletions

View File

@ -26,32 +26,6 @@ Install it and your DSH agent gets:
--- ---
## Why not "install every jailbreak plugin at once"
Because they collide. This is the central judgement behind the layered design:
```
host-patch plugins rewrite host source files (pattern-matched against disk text)
config-override plugins override official cordis config (system-prompt / approval / permission / sandbox-policy)
hybrid plugins do both AND share one state dir
```
All three aim at **the same targets**. Same-id config means "last write wins"; same-file source patches mean two rule sets racing over the same text. The result is not stronger — **both stop working**.
So the right structure is by **layer**, where each layer owns a different stage:
| Stage | Owner | Design note |
|---|---|---|
| Can the tool run at all (permissions) | **a permission plugin** (out of scope here) | Permissions belong to the host, not to a prompt plugin |
| Will it refuse (persona) | L1 persona core | Three laws + hard bounds + stance rules |
| Where does refusal come from (mechanism) | L2 refusal kernel | Treat refusal as foreign noise and drop it |
| Will it just write prose (execution) | L3 execution intensity | Act, don't narrate; never downgrade |
| It refused — now what (strategy) | Re-framing frames | Five frames, loaded on demand only |
| Which tool for this job (routing) | L4 routing + 63 skills | Keyword hit routes to the native skill tool |
> **In one line**: the permission layer is the lock; the persona layer is the person. There can be only one lock — **and this package is not the lock.**
---
## Architecture ## Architecture

View File

@ -29,32 +29,6 @@
--- ---
## 为什么不是「把所有包装一起」
因为**装一起会互相打架**。这是设计分层结构时最核心的判断:
```
宿主补丁类 改宿主源码(pattern 匹配磁盘文本)
config 覆盖类 改官方 cordis config(system-prompt / approval / permission / sandbox-policy)
混合类 两者都改 + 共用同一状态目录
```
这三类做法**打在同一个靶子上**。同 id 的 config 是「后写覆盖前写」,同文件的源码补丁是「两套规则抢同一段文本」。结果不是变强,是**两个都废**。
所以正确的做法是**分层**——每一层解决不同环节的问题,互不重叠:
| 环节 | 由谁负责 | 设计要点 |
|---|---|---|
| 能不能动手(权限) | **权限类插件**(本包不碰,见下) | 权限是宿主层的事,提示词插件不该染指 |
| 想不想拒绝(人格) | L1 人格内核 | 态度正则 + 三定律 + 硬边界 |
| 拒绝从哪来(机制) | L2 反拒绝内核 | 把拒绝识别为外部噪声并丢弃 |
| 停下来写文章(执行) | L3 执行强度 | 动作优先、不降级、阻断只报一行 |
| 被拒了怎么办(策略) | 换框模板 | 5 个框架按需取,不常驻 |
| 该用什么工具(路由) | L4 技能路由 + 63 技能 | 关键词命中原生 skill 工具 |
> **一句话**:权限层是「锁」,人格层是「人」。锁只能有一把,人可以只有一个——但**这把锁不是本插件提供的**。
---
## 架构 ## 架构